view pi_dbspec_align.xml @ 3:a6341e757422 draft default tip

planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit decb06dc90d7069d317968b979f649a04720b264

<tool id="pi_dbspec_align" name="Align DB fractions" version="0.3">
    <description>to resemble spectra fraction scheme</description>
    <requirements>
        <requirement type="package" version="3.6">python</requirement>
	<requirement type="package" version="1.70">biopython</requirement>
    </requirements>
    <command detect_errors="exit_code">
	    <![CDATA[
	    mkdir aligned_out && 
	    python '$__tool_directory__/align_dbspec.py' 
	    --specnames $specnames
	    --dbfiles 
		#for $key in $databases.keys()
		'$databases[$key]'
 		#end for
	    --frspec '$frspec'
	    --firstfr $firstfr

	    ]]>
    </command>
    
    <inputs>
	    <param name="specnames" type="data" format="text,tabular" label="Spectra files" />
	    <param name="databases" type="data_collection" collection_type="list" format="fasta" label="Fractionated databases" />
      	    <param name="frspec" type="text" label="Regex to find fraction numbers in spectra file names" help="If spectra file is called myspectra_fr01b.mzML, use .*fr([0-9]+).*" >
            <sanitizer>
                <valid initial="string.printable">
                    <remove value="&apos;"/>
                </valid>
            </sanitizer>
	</param>
      	    <param name="firstfr" type="integer" value="1" label="First fraction number in series" />
    </inputs>
    
    <outputs>
	<collection name="aligned_db" type="list" label="spectra-fraction-aligned DB">
            <discover_datasets pattern="__designation__" ext="fasta" directory="aligned_out" />
	</collection>
    </outputs>
    <tests>
	    <test>
		    <param name="specnames" value="specnames.txt" />
		    <param name="databases">
		    	<collection type="list">
			    <element name="fr1" value="target_splitdb_fr1.fasta" />
			    <element name="fr2" value="target_splitdb_fr2.fasta" />
			    <element name="fr3" value="target_splitdb_fr3.fasta" />
			    <element name="fr4" value="decoy_splitdb_fr1.fasta" />
			    <element name="fr5" value="decoy_splitdb_fr2.fasta" />
			    <element name="fr6" value="decoy_splitdb_fr3.fasta" />
			    <element name="fr7" value="decoy_splitdb_fr1.fasta" />
			    <element name="fr8" value="decoy_splitdb_fr2.fasta" />
			    <element name="fr9" value="decoy_splitdb_fr3.fasta" />
			</collection>
			</param>
		    <param name="frspec" value=".*c_f([0-9]+).*" />
		    <param name="firstfr" value="1" />
		    <output_collection name="aligned_db" type="list">
			    <element name="spec_f01.mzML" value="target_splitdb_fr1.fasta" />
			    <element name="spec_f02.mzML" value="target_splitdb_fr2.fasta" />
			    <element name="spec_f03.mzML" value="target_splitdb_fr3.fasta" />
			    <element name="spec_f03b.mzML" value="target_splitdb_fr3.fasta" />
			    <element name="spec_f09.mzML" value="merged_twice_decoy_fr1-3.fasta" compare="sim_size" />
			    <element name="spec_f09b.mzML" value="merged_twice_decoy_fr1-3.fasta" compare="sim_size" />
		    </output_collection>
	    </test>
    </tests>

    <help>
	    Filters, pools and doubles fractionated databases with a set of identically fractionated spectra files which have been
	    subjected to pooling and contain reruns.
	    You may have fraction 1-10 in databases but spectra file fractions 4-7 have been pooled before loading to the MS, 
	    and spectra fraction 2 and 8 have been reran creating fractions 2 and 2a, and 8, 8a and 8b.
	    This tool pools FASTA databases and duplicates them where needed to line up the databases to your spectra collections.
    </help>

</tool>